Spatio-Temporal Decision Fusion for Quickest Fault Detection Within Industrial Plants: The Oil and Gas Scenario

In this work, we present a spatio-temporal decision fusion approach aimed at performing quickest detection of faults within an Oil and Gas subsea production system. Specifically, a sensor network collectively monitors the state of different pieces of equipment and reports the collected decisions to a fusion center. Therein, a spatial aggregation is performed and a global decision is taken. Such decisions are then aggregated in time by a post-processing center, which performs quickest detection of system fault according to a Bayesian criterion which exploits change-time statistical distributions originated by system components' datasheets. The performance of our approach is analyzed in terms of both detection- and reliability-focused metrics, with a focus on (fast & inspection-cost-limited) leak detection in a real-world oil platform located in the Barents Sea.